
MCP server for AI memory - store and retrieve context across AI conversations
概览
Give your AI a memory. Works with Claude Desktop and any MCP-compatible client. : ~/Library/Application Support/Claude/claude_desktop_config.json : %APPDATA%\Claude\claude_desktop_config.json Now ask Claude: "Create a project called My App to track my development decisions" - "Save this architecture decision to the project" - "Remember this API design for later" - "Store this bug investigation so I don't forget" - "Search for authentication" - "What did we decide about the database?" - "Load all security-related artifacts" - "Resume my project" - "Show me the project summary" - "What were we working on?" - "Analyze my ChatGPT export at ~/Downloads/chatgpt-export.zip" - "Import the 'React Development' project from my chat history" - "What projects can you detect from my Claude conversations?" - project_save - Create or update a project - project_list - List all projects - project_resume - Load project with summaries - project_analysis_get - Get AI-generated insights
README
以下为原文 README 节选,完整内容请查看原文。
@contextable/mcp
Give your AI a memory. Works with Claude Desktop and any MCP-compatible client.
Quick Start (30 seconds)
Add to your Claude Desktop config:
macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
Windows: %APPDATA%\Claude\claude_desktop_config.json
{
"mcpServers": {
"contextable": {
"command": "npx",
"args": ["@contextable/mcp"]
}
}
}
Restart Claude Desktop. Done.
Now ask Claude: “Create a project called My App to track my development decisions”
What You Can Do
Save context that persists across conversations:
- “Save this architecture decision to the project”
- “Remember this API design for later”
- “Store this bug investigation so I don’t forget”
Find anything instantly:
- “Search for authentication”
- “What did we decide about the database?”
- “Load all security-related artifacts”
Pick up where you left off:
- “Resume my project”
- “Show me the project summary”
- “What were we working on?”
Import your chat history (NEW):
- “Analyze my ChatGPT export at ~/Downloads/chatgpt-export.zip”
- “Import the ‘React Development’ project from my chat history”
- “What projects can you detect from my Claude conversations?”
Features
| Feature | Description |
|---|---|
| Projects | Organize context by project or topic |
| Artifacts | Save decisions, code snippets, docs, conversations |
| Full-Text Search | Find anything across all projects |
| Version History | Every change tracked, rollback anytime |
| Auto-Chunking | Large content automatically split |
| Topic Clustering | Auto-detect themes across artifacts |
| Chat Import | Import from ChatGPT, Claude, Gemini exports |
All 15 Tools
Projects
project_save- Create or update a projectproject_list- List all projectsproject_resume- Load project with summariesproject_analysis_get- Get AI-generated insights
Artifacts
artifact_save- Save content (auto-chunks large files)artifact_list- List with size estimatesartifact_get- Load full contentartifact_delete- Archive (recoverable)artifact_restore- Restore archivedartifact_archived- List archived itemsartifact_versions- View historyartifact_rollback- Restore previous version
Search
search- Full-text search across everything
Import (NEW in v0.2.0)
import_analyze- Analyze chat exports from ChatGPT, Claude, or Geminiimport_seed- Create projects from analyzed chat history
Your Data
Everything is stored locally in SQLite:
~/.contextable/data.db
No account. No cloud. No tracking. Your data stays on your machine.
Want More?
Contextable Cloud adds:
| Feature | Local | Cloud |
|---|---|---|
| Claude Desktop | ✓ | ✓ |
| ChatGPT | - | ✓ |
| Claude.ai (web) | - | ✓ |
| Sync across devices | - | ✓ |
安装
npx @contextable/mcp配置
{
"mcpServers": {
"contextable": {
"command": "npx",
"args": ["@contextable/mcp"]
}
}
}